> For the complete documentation index, see [llms.txt](https://docs.kobotai.co/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.kobotai.co/world/quickstart.md).

# Quickstart

Run a complete, local World Protocol server and query it with WorldDevKit. No account, API key, database or Docker is required.

## Requirements

* Node.js 20 or newer
* pnpm 10.17.1

## Run the starter world

```sh
git clone https://github.com/KobotAI/world-protocol.git
cd world-protocol
corepack enable
pnpm install --frozen-lockfile
pnpm quickstart
```

The world is now available at `http://localhost:8787`. In another terminal, run the client:

```sh
pnpm --dir examples/client-node quickstart
```

You should see the starter places and an opaque pagination cursor.

## Make it yours

The starter has only three files that matter:

| File                                              | Change                                           |
| ------------------------------------------------- | ------------------------------------------------ |
| `examples/minimal-world/src/world.js`             | World metadata, entities and data-source methods |
| `examples/minimal-world/src/server.js`            | Node HTTP adapter; usually leave this alone      |
| `examples/minimal-world/test/conformance.test.js` | Level 1 compatibility test                       |

Start by changing the world name and the `places` array in `src/world.js`. Keep entity IDs stable once clients can see them.

## Test it

```sh
pnpm --dir examples/minimal-world test
```

The test runs fully in-process and needs no open port.

## Deploy it

The starter already reads `PORT`, `HOST` and `WORLD_URL`, so it runs on any Node.js 20 host:

```
Install command: pnpm install --frozen-lockfile && pnpm build
Start command: pnpm --dir examples/minimal-world start
Environment: HOST=0.0.0.0, WORLD_URL=https://your-world.example
```

Your host must route both `/.well-known/world.json` and `/api/world/v0/*` to the process. See [Deploy a world](/world/guides/deploy-a-world.md) for the production checklist.

## Using an AI coding agent

Open the repository in Claude Code, Zed, Codex or another coding agent and give it this prompt:

```
Read AGENTS.md and docs/agents/build-a-world.md. Turn examples/minimal-world into a world named <name>. Use only public @worlddevkit APIs, keep discovery and conformance working, and run pnpm test plus pnpm typecheck before finishing.
```

The repository also publishes `llms.txt` and `llms-full.txt` as compact machine-readable context.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.kobotai.co/world/quickstart.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.